Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Valley
    -0.08
     valley
    -0.07
    Ａ
    -0.07
    assadors
    -0.07
    έντρο
    -0.07
     kì
    -0.07
    اهم
    -0.07
     teenager
    -0.07
    steder
    -0.07
    /********
    -0.07
    POSITIVE LOGITS
    .interfaces
    0.06
     Premium
    0.06
    GetSize
    0.06
    تل
    0.06
    conut
    0.06
    isel
    0.06
     истор
    0.06
    (){}↵↵
    0.06
     deny
    0.06
    .drawString
    0.05
    Act Density 0.000%

    No Known Activations